Blog
LLMs & Texto
Loop the Loopies!
arXiv:2607.16051v1 Announce Type: new Abstract: We present Loopie, the most powerful looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6Bparameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N-fold increase in pre-training compute, increasing the parameter count by a factor of N usually outperforms looping a model N times. Loopie addresses this chall...
arXiv cs.CL
·Zitian Gao, Yilong Chen, Yihao Xiao, Xinyu Yang, Ran Tao, Joey Zhou, Bryan Dai
·
// relacionados
Leia também
Blog
Hugging Face says an AI agent hacked its infrastructure, and it used AI to fight back
Editorial
Cura 1T: um modelo que aprende medicina treinando a si mesmo, sob supervisão humana
Blog
Beyond grep: The case for a context-rich AI coding harness
Blog